Shape agent capabilities into your workflow.

Design MD converts a website, brand guide, screenshots, or a mood-board description into two paired artifacts. DESIGN.md captures semantic tokens, component rules, visual directives, and named anti-patterns for AI agents, while design-showcase.html presents the same system in a self-contained page that humans can open without a server. The shared source tokens help keep implementation guidance and visual review aligned.

Run this skill after a development phase to assign two to seven fresh subagents across specification, architecture, code quality, security, and performance. It selects an S, M, or L workflow from diff size and sensitive areas; larger reviews can add an adversarial skeptic and a fresh regression sweep after fixes. Changes touching authentication, PII, payments, uploads, or raw SQL are bumped to at least medium depth. It is designed for phase boundaries, not CI, PR review, or a replacement for human security review.

Tochi-Satei-Kun reads MLIT transaction data and public-land-price GeoJSON, re-estimates municipality-specific hedonic regression coefficients, selects comparable cases, and exports broker and client worksheets in Excel. The broker sheet exposes coefficients and adjustments so the estimate can be checked, while the client sheet hides statistical detail. It supports Japanese vacant land with ownership rights for preliminary brokerage screening, not a statutory appraisal, and needs current source data supplied by the user.

Point Claude at a function or failing request, and the plugin reads nearby code, selects strategic breakpoints, attaches through the Chrome DevTools Protocol, and waits while you trigger the code path. It then inspects locals, expressions, and the call stack before reporting findings in plain language. The debugger is Node.js-only and requires Node.js 22, a service started with --inspect, and a usable attach configuration in .vscode/launch.json.

Article Autopilot turns a keyword into a Markdown draft by researching the search results, writing to a site-specific voice, auditing E-E-A-T signals, and running language rules before output. A YAML configuration controls the audience, terminology, tone, and frontmatter format. It runs inside Claude Code, depends on upstream content skills, and deliberately leaves publishing to the user.

bpmn-xml-generator turns plain-language process descriptions into BPMN 2.0 XML for Claude Code or Cline. It asks for missing details, validates connectivity, gateway conditions, timer formats, and Camunda extensions, and can add a BPMNDiagram layout for editors such as bpmn.io. The automatic layout path requires Node.js 18 or newer; the core skill works as a Markdown-based agent skill.

Perfect UI helps an agent design and ship landing pages, portfolios, and other page types with a deliberate visual direction. It locks a vibe, palette, typography, custom icons, two-dimensional assets, motion choices, and accessibility details, then runs an anti-slop audit. It also supports URL study mode and component-scoped previews, while the default output targets Next.js, Tailwind, and customized shadcn/ui.

cv-creator builds, improves, reviews, and tailors CVs through one Claude Code skill. It separates regional patterns for US/Canada, UK/EU, Germany, academic applications, and UAE/GCC from industry overlays such as tech, nursing, finance, sales, trades, creative, and executive work. Markdown needs no extra tools; PDF and DOCX output requires pandoc, and PDF also needs a TeX engine. Japanese, Chinese, and India-specific formats are outside v1.

3D Animation Creator turns a video into a single-file Apple-style scroll-animation site whose canvas playback follows scroll position. It adds responsive mobile treatment and annotation cards, can use a URL or pasted text for content, and runs with FFmpeg on macOS or Linux.

Use this skill to draft or review labels, errors, empty states, onboarding, settings, and AI feature copy, with several options and concise tradeoffs. Its guidance is grounded in established US design systems and checks accessibility, inclusive language, and localization risks. It is intended for product interfaces, not blogs, ads, landing pages, or email campaigns.

Use zero-cost-deploy as an agent-driven playbook for shipping a web app with Vercel, Render, Supabase, Upstash, and GitHub Actions free tiers. It covers setup, secrets, database migrations, environment variables, custom domains, smoke tests, and documented workarounds for common deployment failures. The stack still carries free-tier constraints, including Render cold starts, storage and usage caps, single-region operation, and Vercel Hobby's non-commercial terms.

Keito Time Track installs lifecycle hooks for Claude Code and Codex, maps each Git worktree to a Keito company, client, project, and task, and records one agent-sourced time entry when a session ends. Credentials stay with the Keito CLI, while the repository stores only local identifiers in `.keito/config.yml`. Each repository needs its own setup, and the best-effort hooks log failures without breaking the coding session.

buy-me-a-car combines 16 Claude Code skills into a buyer-side workflow for vehicle research, quote collection, out-the-door calculations, dealer replies, CARFAX review, insurance, and closing checks. The full flow searches multiple sites and creates Gmail drafts for review rather than sending binding messages automatically. It is a single-author alpha, and fee, incentive, and eligibility data can drift, so figures should be verified before signing.

Portfolio README Writer documents a finished project for either a personal portfolio audience or a hackathon judge. It reads the repository, asks only for details it cannot infer, and writes a structured README with a pitch, quick start, stack, architecture, caveats, and mode-specific sections. It avoids emoji and inflated language, shows a diff before replacing an existing README, and does not modify code, media, or deployment.

Use mdrise when a README, report, or article needs a polished web version without changing its wording. The Claude skill chooses a visual treatment based on the document type, adds a floating table of contents, supports many writing systems, and embeds a source hash so unchanged Markdown is not rendered again unnecessarily.

Use this lightweight skill when you already know the gameplay-video workflow and want a concise output. It delivers six image prompts, video prompts, and a minimal UI dictionary while keeping four-view character references, HUD anchors, opening-frame guidance, and aspect-ratio constraints. It omits process explanations, checklists, generation steps, and post-production notes to save context.

Deck Pipeline takes a Chinese presentation through design analysis, page-by-page English rewriting, layout checks, and a documented handoff. It produces edited PPTX files and a bilingual comparison workbook, while a polish-only mode can clean up single-language decks without translating them. Slide checkpoints let users correct terminology or direction before changes spread across the deck.

Urd activates when an agent moves from a plan or design into implementation and encounters an uncovered edge case, contradiction, unsanctioned fallback, weakened test, or uncertain workaround. It prompts the agent to explain the exact step, quote the relevant specification, describe the gap, present options, and recommend a choice while separating verified facts from beliefs. This is a behavioral guardrail rather than a runtime guarantee, and it deliberately trades extra clarification rounds for fewer silent deviations.